Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels

Fengming Lin, Yan Xia, Nishant Ravikumar, Qiongyao Liu, Michael MacRaild, Alejandro F Frangi

Research output: Working paperPreprint

17 Downloads (Pure)

Abstract

Accurate segmentation of brain vessels is crucial for cerebrovascular disease diagnosis and treatment. However, existing methods face challenges in capturing small vessels and handling datasets that are partially or ambiguously annotated. In this paper, we propose an adaptive semi-supervised approach to address these challenges. Our approach incorporates innovative techniques including progressive semi-supervised learning, adaptative training strategy, and boundary enhancement. Experimental results on 3DRA datasets demonstrate the superiority of our method in terms of mesh-based segmentation metrics. By leveraging the partially and ambiguously labeled data, which only annotates the main vessels, our method achieves impressive segmentation performance on mislabeled fine vessels, showcasing its potential for clinical applications.
Original languageEnglish
Publication statusPublished - 7 Aug 2023

Keywords

  • eess.IV
  • cs.CV
  • cs.LG

Fingerprint

Dive into the research topics of 'Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels'. Together they form a unique fingerprint.

Cite this